cs.LG（2024-02-16）

📊 共 22 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱二：RL算法与架构 (RL & Architecture) (13) 支柱九：具身大模型 (Embodied Foundation Models) (5 🔗1) 支柱八：物理动画 (Physics-based Animation) (2) 支柱一：机器人控制 (Robot Control) (1 🔗1) 支柱七：动作重定向 (Motion Retargeting) (1)

🔬 支柱二：RL算法与架构 (RL & Architecture) (13 篇)

#题目一句话要点标签🔗⭐
1 Surpassing legacy approaches to PWR core reload optimization with single-objective Reinforcement learning 基于强化学习的核反应堆核心重装优化方法 reinforcement learning deep reinforcement learning DRL
2 Goal-Conditioned Reinforcement Learning from Sub-Optimal Data on Metric Spaces 提出MetricRL以解决稀疏奖励下的次优数据学习问题 reinforcement learning offline reinforcement learning imitation learning
3 Active Preference Optimization for Sample Efficient RLHF 提出主动偏好优化以解决样本效率低下问题 reinforcement learning RLHF large language model
4 Adversarial Curriculum Graph Contrastive Learning with Pair-wise Augmentation 提出对抗性课程图对比学习以解决样本生成相似性控制问题 representation learning contrastive learning curriculum learning
5 Parametric Augmentation for Time Series Contrastive Learning 提出AutoTCL以解决时间序列对比学习中的数据增强问题 representation learning MAE contrastive learning
6 Optimizing Warfarin Dosing Using Contextual Bandit: An Offline Policy Learning and Evaluation Method 利用上下文赌博机优化华法林剂量以解决个体化用药问题 reinforcement learning policy learning
7 RLVF: Learning from Verbal Feedback without Overgeneralization 提出C3PO方法以解决语言反馈过度泛化问题 reinforcement learning RLHF large language model
8 Policy Learning for Off-Dynamics RL with Deficient Support 提出一种新方法以解决动态不匹配的强化学习问题 reinforcement learning policy learning
9 Implicit Causal Representation Learning via Switchable Mechanisms 提出隐式因果表示学习方法以解决软干预挑战 representation learning
10 FedD2S: Personalized Data-Free Federated Knowledge Distillation 提出FedD2S以解决联邦学习中的数据异质性问题 distillation
11 Double Duality: Variational Primal-Dual Policy Optimization for Constrained Reinforcement Learning 提出变分原始-对偶策略优化以解决约束强化学习问题 reinforcement learning
12 Rethinking Self-Distillation: Label Averaging and Enhanced Soft Label Refinement with Partial Labels 提出自蒸馏新方法以解决标签噪声问题 distillation
13 Privacy for Fairness: Information Obfuscation for Fair Representation Learning with Local Differential Privacy 提出信息模糊化方法以解决公平性与隐私保护问题 representation learning

🔬 支柱九：具身大模型 (Embodied Foundation Models) (5 篇)

#题目一句话要点标签🔗⭐
14 Interpreting CLIP with Sparse Linear Concept Embeddings (SpLiCE) 提出SpLiCE以提高CLIP表示的可解释性 multimodal
15 LLMDFA: Analyzing Dataflow in Code with Large Language Models 提出LLMDFA以解决编译无关的数据流分析问题 large language model chain-of-thought ✅
16 QDyLoRA: Quantized Dynamic Low-Rank Adaptation for Efficient Large Language Model Tuning 提出QDyLoRA以解决大语言模型调优中的内存限制问题 large language model
17 The Evolution of Statistical Induction Heads: In-Context Learning Markov Chains 提出马尔可夫链序列建模任务以研究上下文学习能力 large language model
18 Any-Precision LLM: Low-Cost Deployment of Multiple, Different-Sized LLMs 提出Any-Precision LLM以降低多种尺寸LLM的部署成本 large language model

🔬 支柱八：物理动画 (Physics-based Animation) (2 篇)

#题目一句话要点标签🔗⭐
19 Graph-based Forecasting with Missing Data through Spatiotemporal Downsampling 提出层次化时空下采样以解决缺失数据的预测问题 spatiotemporal
20 A Predictive Surrogate Model for Heat Transfer of an Impinging Jet on a Concave Surface 提出预测代理模型以解决冲击喷流热传递问题 PULSE

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
21 PRISE: LLM-Style Sequence Compression for Learning Temporal Action Abstractions in Control 提出PRISE以解决连续控制中的时间动作抽象问题 manipulation imitation learning ✅

🔬 支柱七：动作重定向 (Motion Retargeting) (1 篇)

#题目一句话要点标签🔗⭐
22 RPMixer: Shaking Up Time Series Forecasting with Random Projections for Large Spatial-Temporal Data 提出RPMixer以解决大规模时空数据预测问题 spatial relationship

⬅️ 返回 cs.LG 首页 · 🏠 返回主页